A Bayesian regularized feed-forward neural network model for conductivity prediction of PS/MWCNT nanocomposite film coatings

Barış Demirbay*, Duygu Bayram Kara, Şaziye Uğur

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

21 Citations (Scopus)

Abstract

In our present work, a multi-layered feed-forward neural network (FFNN) model was designed and developed to predict electrical conductivity of multi-walled carbon nanotube (MWCNT) doped polystyrene (PS) latex nanocomposite (PS/MWCNT) film coatings using data set gathered from several conductivity measurements. Surfactant concentrations (Cs), initiator concentrations (Ci), molecular weights (MPS) and particle sizes of PS latex (DPS) together with MWCNT concentrations (RMWCNT) were introduced as inputs while electrical conductivity (σ) was assigned as a single output in FFNN topology. Network training was carried out using a Bayesian regulation backpropagation algorithm. Optimal geometry of the hidden layer was first studied to search out the best FFNN topology providing the most accurate performance results. Mean squared error, MSE, mean absolute error, MAE, root-mean-squared error, RMSE, determination of coefficient, R2, variance accounted for, VAF, and regression analysis were employed as performance assessment parameters for proposed network model. Correlation coefficients (r) of each input variable together with relative importance-based sensitivity analysis results have shown that RMWCNT is the most significant input variable strongly affecting the σ value of PS/MWCNT nanocomposite film coatings and training performance of the neural network. Mathematical explicit function has been derived to model electrical conductivity by using weights and bias values at each neuron found in FFNN development. All predicted conductivity values are in a very good agreement with measured conductivity values, showing robustness and reliability of suggested FFNN model and it can be effectively used to predict electrical conductivity of PS/MWCNT nanocomposite film coatings.

Original languageEnglish
Article number106632
JournalApplied Soft Computing
Volume96
DOIs
Publication statusPublished - Nov 2020

Bibliographical note

Publisher Copyright:
© 2020 Elsevier B.V.

Funding

Every challenging scientific work requires the guidance of hard-working and encouraging professors who always come up with insightful advice, bring up solutions for current problems and make the impossible things real. Two of us, B.D. and D.B.K., as her former M.Sc. student and colleague, would like to dedicate this research article to the memory of our dear supervisor and colleague Prof. Dr. Şaziye Uğur who had unfortunately passed away shortly before this paper has been accepted for publication. This work has been financed by a scientific research coordination unit with a project number of 40176 at Istanbul Technical University (ITU) . The authors would like to thank Prof. Dr. Selim Kara and his research unit for conductivity measurements and fruitful discussions.

FundersFunder number
Istanbul Teknik Üniversitesi

    Keywords

    • Artificial neural network
    • Bayesian regulation
    • Electrical conductivity
    • Electrical percolation
    • Film formation
    • Mathematical modeling
    • Polymer nanocomposites
    • Polymer physics
    • Regression
    • Soft computing

    Fingerprint

    Dive into the research topics of 'A Bayesian regularized feed-forward neural network model for conductivity prediction of PS/MWCNT nanocomposite film coatings'. Together they form a unique fingerprint.

    Cite this